Upload PPO LunarLander-v2 trained agen
Browse files- .gitattributes +1 -0
- LunarLander-v2-rainbow.zip +3 -0
- LunarLander-v2-rainbow/_stable_baselines3_version +1 -0
- LunarLander-v2-rainbow/data +94 -0
- LunarLander-v2-rainbow/policy.optimizer.pth +3 -0
- LunarLander-v2-rainbow/policy.pth +3 -0
- LunarLander-v2-rainbow/pytorch_variables.pth +3 -0
- LunarLander-v2-rainbow/system_info.txt +7 -0
- README.md +36 -0
- config.json +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
LunarLander-v2-rainbow.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dd3665a91016248c05df243f57e2dae3b0330eb489a0b9d9fde51e1bf811477
|
3 |
+
size 144144
|
LunarLander-v2-rainbow/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
LunarLander-v2-rainbow/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
+
"__module__": "stable_baselines3.common.policies",
|
6 |
+
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f95346b1440>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f95346b14d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f95346b1560>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f95346b15f0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f95346b1680>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f95346b1710>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f95346b17a0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f95346b1830>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f95346b18c0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f95346b1950>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f95346b19e0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f95346f4c30>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1656740963.1297853,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gASVeBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMItoR80LOjZECUhpRSlIwBbJRN6AOMAXSUR0CYeCpxm03PdX2UKGgGaAloD0MIOKEQAYeXYECUhpRSlGgVTegDaBZHQJh6DSApazN1fZQoaAZoCWgPQwh7MCk+PmlaQJSGlFKUaBVN6ANoFkdAmHqO2AoXsXV9lChoBmgJaA9DCLX66qpA92JAlIaUUpRoFU3oA2gWR0CYe0+Eh7mddX2UKGgGaAloD0MIHH3MBwTXXkCUhpRSlGgVTegDaBZHQJh76tV7x/d1fZQoaAZoCWgPQwhZTGw+Lt5iQJSGlFKUaBVN6ANoFkdAmH9DCHh0hnV9lChoBmgJaA9DCAx4mWGjaWFAlIaUUpRoFU3oA2gWR0CYf22+wkgPdX2UKGgGaAloD0MIbM7BM6FUWkCUhpRSlGgVTegDaBZHQJiYtdyDIzZ1fZQoaAZoCWgPQwjRzmkWaBNlQJSGlFKUaBVN6ANoFkdAmJnmXokiU3V9lChoBmgJaA9DCIyFIXL6IGNAlIaUUpRoFU3oA2gWR0CYmehaTwDvdX2UKGgGaAloD0MISdv4E5VMVUCUhpRSlGgVS+loFkdAmJzS7GvOhXV9lChoBmgJaA9DCOCgvfp4/WBAlIaUUpRoFU3oA2gWR0CYoVNDtw71dX2UKGgGaAloD0MIgQncuhtIYkCUhpRSlGgVTegDaBZHQJijOJFb3XZ1fZQoaAZoCWgPQwgmyAio8F9kQJSGlFKUaBVN6ANoFkdAmKQRPj4pMHV9lChoBmgJaA9DCGoy422ls2RAlIaUUpRoFU3oA2gWR0CYpE5kbxVidX2UKGgGaAloD0MI4Qm9/iQ+GMCUhpRSlGgVTQkBaBZHQJin7BMzuWt1fZQoaAZoCWgPQwgL8N3mjcddQJSGlFKUaBVN6ANoFkdAmKjSXY150XV9lChoBmgJaA9DCNGRXP5D6lxAlIaUUpRoFU3oA2gWR0CYrJ7tiQT3dX2UKGgGaAloD0MIhsd+Fkt9SECUhpRSlGgVS+toFkdAmLTtHYpUgnV9lChoBmgJaA9DCD81XrpJyltAlIaUUpRoFU3oA2gWR0CYvruanaWYdX2UKGgGaAloD0MIT83lBsMRZ0CUhpRSlGgVTegDaBZHQJjAxa2WpqB1fZQoaAZoCWgPQwgsnQ/PEuJWQJSGlFKUaBVN6ANoFkdAmMFX6/IsAnV9lChoBmgJaA9DCBTtKqT8qmJAlIaUUpRoFU3oA2gWR0CYwiZeAuqWdX2UKGgGaAloD0MIysStgpgnYkCUhpRSlGgVTegDaBZHQJjC0wZflZJ1fZQoaAZoCWgPQwhr09heC89jQJSGlFKUaBVN6ANoFkdAmMbn/giu+3V9lChoBmgJaA9DCMto5POKg0dAlIaUUpRoFUveaBZHQJjOn3vhIe51fZQoaAZoCWgPQwhFR3L5D3pmQJSGlFKUaBVN6ANoFkdAmM78FINEw3V9lChoBmgJaA9DCGBa1Ce5YGRAlIaUUpRoFU3oA2gWR0CY4vo9s7+2dX2UKGgGaAloD0MIyQBQxQ00YkCUhpRSlGgVTegDaBZHQJjmdDQZ4wB1fZQoaAZoCWgPQwg9nMB0WmpmQJSGlFKUaBVN6ANoFkdAmOtsIRh+fHV9lChoBmgJaA9DCCQO2UA6xWFAlIaUUpRoFU3oA2gWR0CY7X/JNj9XdX2UKGgGaAloD0MIYMlVLH7pYUCUhpRSlGgVTegDaBZHQJjuXyvs7dV1fZQoaAZoCWgPQwiWCFT/oFhjQJSGlFKUaBVN6ANoFkdAmO6VJtix3XV9lChoBmgJaA9DCIVdFD1wtGJAlIaUUpRoFU3oA2gWR0CY8iydFvycdX2UKGgGaAloD0MI8Z4DyxFyH8CUhpRSlGgVTRYBaBZHQJj2AsEq2Bt1fZQoaAZoCWgPQwhaKQRyiR1ZQJSGlFKUaBVN6ANoFkdAmPdmVu76HnV9lChoBmgJaA9DCI+NQLyuTz5AlIaUUpRoFU0bAWgWR0CY/b3Kji4sdX2UKGgGaAloD0MItoR80LMBI8CUhpRSlGgVS+xoFkdAmP9e/xlQM3V9lChoBmgJaA9DCPkTlQ1rfmJAlIaUUpRoFU3oA2gWR0CZAGBMi8nNdX2UKGgGaAloD0MIi90+q0xLY0CUhpRSlGgVTegDaBZHQJkJ0IfKZD11fZQoaAZoCWgPQwgEIVnAhMdjQJSGlFKUaBVN6ANoFkdAmQvc0+C9RXV9lChoBmgJaA9DCL6FdePd82FAlIaUUpRoFU3oA2gWR0CZDHRUFSsKdX2UKGgGaAloD0MIq1/pfPi2ZECUhpRSlGgVTegDaBZHQJkNR+az/qB1fZQoaAZoCWgPQwhPHhZqzephQJSGlFKUaBVN6ANoFkdAmRILW/ag3HV9lChoBmgJaA9DCDo+Wpwx9F1AlIaUUpRoFU3oA2gWR0CZGcTQE6kqdX2UKGgGaAloD0MIf6FHjJ5jWUCUhpRSlGgVTegDaBZHQJkaGkgwGnp1fZQoaAZoCWgPQwjmQA+1bftkQJSGlFKUaBVN6ANoFkdAmRtl9BrvcHV9lChoBmgJaA9DCP0tAfinRFxAlIaUUpRoFU3oA2gWR0CZNgeHi3ocdX2UKGgGaAloD0MIyXTo9Dx6Z0CUhpRSlGgVTegDaBZHQJk39EKE3851fZQoaAZoCWgPQwjAP6VKlMldQJSGlFKUaBVN6ANoFkdAmTj+JYT0x3V9lChoBmgJaA9DCIZVvJF5sl1AlIaUUpRoFU3oA2gWR0CZQQgqVhTgdX2UKGgGaAloD0MISaKXUSx4ZECUhpRSlGgVTegDaBZHQJlCf0TURWd1fZQoaAZoCWgPQwgiADj27C1iQJSGlFKUaBVN6ANoFkdAmUineWOZLXV9lChoBmgJaA9DCOIeSx+6I2RAlIaUUpRoFU3oA2gWR0CZSjkcCHRDdX2UKGgGaAloD0MIEW4yqgwvXUCUhpRSlGgVTegDaBZHQJlLIi3XqaB1fZQoaAZoCWgPQwhya9JtiWQrQJSGlFKUaBVL52gWR0CZTaQj2SMcdX2UKGgGaAloD0MIYygn2lW8Z0CUhpRSlGgVTegDaBZHQJlTdEZzgdh1fZQoaAZoCWgPQwh5lEp4Qq/sP5SGlFKUaBVLvWgWR0CZVQ8IzFdcdX2UKGgGaAloD0MIMuauJeSD/7+UhpRSlGgVS+xoFkdAmVUruYx+KHV9lChoBmgJaA9DCNyhYTFqDWBAlIaUUpRoFU3oA2gWR0CZVUtiQT24dX2UKGgGaAloD0MIv/T25yKMYUCUhpRSlGgVTegDaBZHQJlVxxiobXJ1fZQoaAZoCWgPQwiJz51gf/1hQJSGlFKUaBVN6ANoFkdAmVaDlHSWq3V9lChoBmgJaA9DCDkroib6bGVAlIaUUpRoFU3oA2gWR0CZWuifQKKHdX2UKGgGaAloD0MIRgpl4esDIkCUhpRSlGgVTRMBaBZHQJlhZEroW591fZQoaAZoCWgPQwj44/bLJwMiwJSGlFKUaBVL/mgWR0CZYgoZQ53ldX2UKGgGaAloD0MIWcNF7ullZECUhpRSlGgVTegDaBZHQJliiHCXQdF1fZQoaAZoCWgPQwj4GoLjspBgQJSGlFKUaBVN6ANoFkdAmWLbgCOmznV9lChoBmgJaA9DCClf0EICAWBAlIaUUpRoFU3oA2gWR0CZZAWQOnVHdX2UKGgGaAloD0MIRQ4RNyfjZUCUhpRSlGgVTegDaBZHQJl+k5imVJN1fZQoaAZoCWgPQwgIAI49+0ViQJSGlFKUaBVN6ANoFkdAmYCnvphWo3V9lChoBmgJaA9DCABvgQTFhztAlIaUUpRoFUvmaBZHQJmBuBvrGBF1fZQoaAZoCWgPQwh4Qq8/iYhjQJSGlFKUaBVN6ANoFkdAmYHJVjqfOHV9lChoBmgJaA9DCMGsUKR7BGZAlIaUUpRoFU3oA2gWR0CZjBzMRpUQdX2UKGgGaAloD0MI5Nak2xLtYECUhpRSlGgVTegDaBZHQJmVe74BV+91fZQoaAZoCWgPQwgkSKXYURJkQJSGlFKUaBVN6ANoFkdAmZofHxSYPXV9lChoBmgJaA9DCO4/Mh06zmRAlIaUUpRoFU3oA2gWR0CZo7tJ4B3idX2UKGgGaAloD0MIyqZc4V0JaECUhpRSlGgVTegDaBZHQJmkBRQ79yd1fZQoaAZoCWgPQwiN1HsqJ0FkQJSGlFKUaBVN6ANoFkdAmaScaXKKYXV9lChoBmgJaA9DCAt72uGvVWVAlIaUUpRoFU3oA2gWR0CZpXZzxPO6dX2UKGgGaAloD0MIgQpHkMrHYkCUhpRSlGgVTegDaBZHQJmqbmdRR/F1fZQoaAZoCWgPQwgHYtnMoRZjQJSGlFKUaBVN6ANoFkdAmbEUofCAMHV9lChoBmgJaA9DCDtSfecXDWVAlIaUUpRoFU3oA2gWR0CZshsLORkmdX2UKGgGaAloD0MIl8lwPB9OY0CUhpRSlGgVTegDaBZHQJmyao86mwd1fZQoaAZoCWgPQwie8BKc+mtgQJSGlFKUaBVN6ANoFkdAmbOQIhQm/nV9lChoBmgJaA9DCFoO9FDb+VxAlIaUUpRoFU3oA2gWR0CZzcwFkhA4dX2UKGgGaAloD0MI1ouhnOg9Y0CUhpRSlGgVTegDaBZHQJnPxnAZbY91fZQoaAZoCWgPQwg1lrA2xlNkQJSGlFKUaBVN6ANoFkdAmdDerU9ZBHV9lChoBmgJaA9DCI0N3eyPR2FAlIaUUpRoFU3oA2gWR0CZ0PAWBSUDdX2UKGgGaAloD0MIJsPxfAZXZECUhpRSlGgVTegDaBZHQJna6yD7Ikt1fZQoaAZoCWgPQwih2AqaFmJgQJSGlFKUaBVN6ANoFkdAmePuLFXJYHV9lChoBmgJaA9DCFnABG5dcGVAlIaUUpRoFU3oA2gWR0CZ6Gp71Iy1dX2UKGgGaAloD0MIeouH9xyWYUCUhpRSlGgVTegDaBZHQJnxxCOWBz51fZQoaAZoCWgPQwgCYhIu5D1gQJSGlFKUaBVN6ANoFkdAmfIK7dznzXV9lChoBmgJaA9DCJgxBWscu2BAlIaUUpRoFU3oA2gWR0CZ8qR4QjD9dX2UKGgGaAloD0MIEK6AQj2xX0CUhpRSlGgVTegDaBZHQJnzg163RXx1fZQoaAZoCWgPQwixFwrYDkRfQJSGlFKUaBVN6ANoFkdAmfh8aS9ug3V9lChoBmgJaA9DCPj578Fr419AlIaUUpRoFU3oA2gWR0CZ/1/iHZbqdX2UKGgGaAloD0MIWTMyyF3fX0CUhpRSlGgVTegDaBZHQJoAeMo+fRN1fZQoaAZoCWgPQwhK628JwPJhQJSGlFKUaBVN6ANoFkdAmgDKV6eGwnV9lChoBmgJaA9DCGTo2EGlv2BAlIaUUpRoFU3oA2gWR0CaAgIl+mWMdWUu"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 176,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
LunarLander-v2-rainbow/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c674a3e32372738d6317413658f2dd5085b0b2d778c2f4d80c6957242ce9e8d4
|
3 |
+
size 84829
|
LunarLander-v2-rainbow/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eafa8f6c9e5a9fa287be10296caddac744d595e9f741d0d85d70c491b39f764
|
3 |
+
size 43201
|
LunarLander-v2-rainbow/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
LunarLander-v2-rainbow/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 218.30 +/- 40.91
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f95346b1440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f95346b14d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f95346b1560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f95346b15f0>", "_build": "<function ActorCriticPolicy._build at 0x7f95346b1680>", "forward": "<function ActorCriticPolicy.forward at 0x7f95346b1710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f95346b17a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f95346b1830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f95346b18c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f95346b1950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f95346b19e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f95346f4c30>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1656740963.1297853, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 176, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8332b97db717fcbdb8c9395e5697a9bf79f33677bbb42d1fd2869b1d8c42a077
|
3 |
+
size 239027
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 218.29951794522725, "std_reward": 40.90978780893089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-02T06:03:36.959658"}
|